@inproceedings{raychaudhuri-etal-2021-language,
title = "Language-Aligned Waypoint ({LAW}) Supervision for Vision-and-Language Navigation in Continuous Environments",
author = "Raychaudhuri, Sonia and
Wani, Saim and
Patel, Shivansh and
Jain, Unnat and
Chang, Angel",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.328",
doi = "10.18653/v1/2021.emnlp-main.328",
pages = "4018--4028",
abstract = "In the Vision-and-Language Navigation (VLN) task an embodied agent navigates a 3D environment, following natural language instructions. A challenge in this task is how to handle {`}off the path{'} scenarios where an agent veers from a reference path. Prior work supervises the agent with actions based on the shortest path from the agent{'}s location to the goal, but such goal-oriented supervision is often not in alignment with the instruction. Furthermore, the evaluation metrics employed by prior work do not measure how much of a language instruction the agent is able to follow. In this work, we propose a simple and effective language-aligned supervision scheme, and a new metric that measures the number of sub-instructions the agent has completed during navigation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raychaudhuri-etal-2021-language">
<titleInfo>
<title>Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sonia</namePart>
<namePart type="family">Raychaudhuri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saim</namePart>
<namePart type="family">Wani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shivansh</namePart>
<namePart type="family">Patel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Unnat</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angel</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the Vision-and-Language Navigation (VLN) task an embodied agent navigates a 3D environment, following natural language instructions. A challenge in this task is how to handle ‘off the path’ scenarios where an agent veers from a reference path. Prior work supervises the agent with actions based on the shortest path from the agent’s location to the goal, but such goal-oriented supervision is often not in alignment with the instruction. Furthermore, the evaluation metrics employed by prior work do not measure how much of a language instruction the agent is able to follow. In this work, we propose a simple and effective language-aligned supervision scheme, and a new metric that measures the number of sub-instructions the agent has completed during navigation.</abstract>
<identifier type="citekey">raychaudhuri-etal-2021-language</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.328</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.328</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4018</start>
<end>4028</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments
%A Raychaudhuri, Sonia
%A Wani, Saim
%A Patel, Shivansh
%A Jain, Unnat
%A Chang, Angel
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F raychaudhuri-etal-2021-language
%X In the Vision-and-Language Navigation (VLN) task an embodied agent navigates a 3D environment, following natural language instructions. A challenge in this task is how to handle ‘off the path’ scenarios where an agent veers from a reference path. Prior work supervises the agent with actions based on the shortest path from the agent’s location to the goal, but such goal-oriented supervision is often not in alignment with the instruction. Furthermore, the evaluation metrics employed by prior work do not measure how much of a language instruction the agent is able to follow. In this work, we propose a simple and effective language-aligned supervision scheme, and a new metric that measures the number of sub-instructions the agent has completed during navigation.
%R 10.18653/v1/2021.emnlp-main.328
%U https://aclanthology.org/2021.emnlp-main.328
%U https://doi.org/10.18653/v1/2021.emnlp-main.328
%P 4018-4028
Markdown (Informal)
[Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments](https://aclanthology.org/2021.emnlp-main.328) (Raychaudhuri et al., EMNLP 2021)
ACL